bytedance / tarsier
Tarsier -- a family of large-scale video-language models, which is designed to generate high-quality video descriptions , together with good capability of general video understanding.
☆338Updated last week
Alternatives and similar repositories for tarsier:
Users that are interested in tarsier are comparing it to the libraries listed below
- Long Context Transfer from Language to Vision☆368Updated 2 weeks ago
- ☆366Updated last month
- VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling☆378Updated this week
- Official repository for the paper PLLaVA☆644Updated 8 months ago
- This is the official implementation of "Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams"☆175Updated 3 months ago
- 🔥🔥First-ever hour scale video understanding models☆268Updated this week
- SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models☆208Updated 6 months ago
- Official Repository of paper VideoGPT+: Integrating Image and Video Encoders for Enhanced Video Understanding☆265Updated this week
- ✨✨[CVPR 2025] Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis☆493Updated last week
- Multimodal Models in Real World☆455Updated last month
- [CVPR 2024] TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding☆353Updated 4 months ago
- ☆182Updated 8 months ago
- Frontier Multimodal Foundation Models for Image and Video Understanding☆680Updated last week
- Official code for Goldfish model for long video understanding and MiniGPT4-video for short video understanding☆604Updated 3 months ago
- [ACL 2024] GroundingGPT: Language-Enhanced Multi-modal Grounding Model☆323Updated 4 months ago
- This is the official code of VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding (ECCV 2024)☆183Updated 3 months ago
- A new multi-shot video understanding benchmark Shot2Story with comprehensive video summaries and detailed shot-level captions.☆125Updated 2 months ago
- NeurIPS 2024 Paper: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing☆517Updated 5 months ago
- [CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding☆605Updated 2 months ago
- LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models (ECCV 2024)☆788Updated 8 months ago
- Official repo for paper "MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions"☆422Updated 7 months ago
- [ICLR 2025] VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation☆255Updated 2 months ago
- ☆140Updated 2 months ago
- LinVT: Empower Your Image-level Large Language Model to Understand Videos☆67Updated 3 months ago
- [CVPR'2024 Highlight] Official PyTorch implementation of the paper "VTimeLLM: Empower LLM to Grasp Video Moments".☆264Updated 9 months ago
- LLaVA-UHD v2: an MLLM Integrating High-Resolution Semantic Pyramid via Hierarchical Window Transformer☆370Updated 2 weeks ago
- PG-Video-LLaVA: Pixel Grounding in Large Multimodal Video Models☆256Updated last year
- LLM2CLIP makes SOTA pretrained CLIP model more SOTA ever.☆495Updated last week
- [CVPR 2024] Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers☆587Updated 5 months ago
- Video-R1: Reinforcing Video Reasoning in MLLMs [🔥the first work to systematically explore R1 for video]☆205Updated this week